Model comparison

Codellama 70b Instruct vs Phi 3 Mini 4k Instruct

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 27.9 on the Noometry Index.

Last verified . 5 shared benchmarks.

Codellama 70b Instruct Meta

33.7

Rank #237 Confirmed

Phi 3 Mini 4k Instruct Microsoft

27.9

Rank #328 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Codellama 70b Instruct scores higher in 4 categories and Phi 3 Mini 4k Instruct in 1 category; 5 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Codellama 70b Instruct leads 37.6 to 26.6.

Side by side

Codellama 70b Instruct and Phi 3 Mini 4k Instruct specifications
Codellama 70b InstructPhi 3 Mini 4k Instruct
ProviderMetaMicrosoft
Noometry Index33.727.9
Released—2024-04-23
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked735

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Codellama 70b Instruct leads

Codellama 70b Instruct: 37.6 (#193), Phi 3 Mini 4k Instruct: 26.6 (#323)

Coding benchmarks
BenchmarkCodellama 70b InstructPhi 3 Mini 4k Instruct
HumanEval+65.9%59.1%
BigCodeBench Instruct40.7%—
LiveBench Coding—15.5%
LMArena Coding—1093
BigCodeBench Complete49.6%—
MBPP+—54.2%

Reasoning Codellama 70b Instruct leads

Codellama 70b Instruct: 20.1 (#242), Phi 3 Mini 4k Instruct: 14.1 (#328)

Reasoning benchmarks
BenchmarkCodellama 70b InstructPhi 3 Mini 4k Instruct
LMArena Hard Prompts10521072
Chess Puzzles—0%
LiveBench Reasoning—26.8%
LiveBench Data Analysis—34.7%
Adversarial NLI—52.8%
BIG-Bench Hard—71.7%
HellaSwag—76.7%
LiveBench—22.4%
WinoGrande—70.8%

Math Not comparable

Codellama 70b Instruct: —, Phi 3 Mini 4k Instruct: 26.6 (#257)

Math benchmarks
BenchmarkCodellama 70b InstructPhi 3 Mini 4k Instruct
LiveBench Math—15.7%
LMArena Math—1111

Knowledge Not comparable

Codellama 70b Instruct: —, Phi 3 Mini 4k Instruct: 28.5 (#246)

Knowledge benchmarks
BenchmarkCodellama 70b InstructPhi 3 Mini 4k Instruct
LMArena Expert—1045
ARC (AI2) Challenge—84.9%
MMLU—68.8%
OpenBookQA—88%
TriviaQA—64%

Multilingual Phi 3 Mini 4k Instruct leads

Codellama 70b Instruct: 24.8 (#288), Phi 3 Mini 4k Instruct: 26.3 (#280)

Multilingual benchmarks
BenchmarkCodellama 70b InstructPhi 3 Mini 4k Instruct
LMArena Non-English9921021
LMArena Chinese—1021
LMArena French—1076
LMArena German—1044
LMArena Japanese—935
LMArena Korean—905
LMArena Russian—1022
LMArena Spanish—1085

Instruction Following Codellama 70b Instruct leads

Codellama 70b Instruct: 51.9 (#293), Phi 3 Mini 4k Instruct: 47.7 (#303)

Instruction Following benchmarks
BenchmarkCodellama 70b InstructPhi 3 Mini 4k Instruct
LMArena Instruction Following10241053
LiveBench Instruction Following—39.1%

Long Context Not comparable

Codellama 70b Instruct: —, Phi 3 Mini 4k Instruct: 31.7 (#276)

Long Context benchmarks
BenchmarkCodellama 70b InstructPhi 3 Mini 4k Instruct
LMArena Longer Query—1044

Writing & Preference Codellama 70b Instruct leads

Codellama 70b Instruct: 33.4 (#277), Phi 3 Mini 4k Instruct: 27.6 (#300)

Writing & Preference benchmarks
BenchmarkCodellama 70b InstructPhi 3 Mini 4k Instruct
LMArena Text10571073
LMArena Creative Writing—1037
LMArena Multi-Turn—1018
LiveBench Language—9.2%

Frequently asked questions

Is Codellama 70b Instruct better than Phi 3 Mini 4k Instruct?

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 27.9 on the Noometry Index.

Is Codellama 70b Instruct or Phi 3 Mini 4k Instruct better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 26.6 in the Noometry coding category.

How many benchmarks do Codellama 70b Instruct and Phi 3 Mini 4k Instruct share?

5 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.

Related comparisons

Go deeper